Related papers: ENOVA: Autoscaling towards Cost-effective and Stab…

As large language models (LLMs) continue to grow in size, distributed inference has become increasingly important. Model-parallel strategies must now efficiently scale not only across multiple GPUs but also across multiple nodes. In this…

Large Language Models (LLMs) have gained immense success in revolutionizing various applications, including content generation, search and recommendation, and AI-assisted operation. To reduce high training costs, Mixture-of-Experts (MoE)…

The advent of powerful, accessible Large Language Models (LLMs) like Google's Gemini presents new opportunities for democratizing financial data analysis. This paper documents the design, implementation, and iterative debugging of a novel,…

High-throughput inference serving is essential for applications built on large language models (LLMs). Existing serving frameworks reduce request-level and batch-level bubbles through batching and scheduling, but often overlook bubbles…

This paper presents Block, a distributed scheduling framework designed to optimize load balancing and auto-provisioning across instances in large language model serving frameworks by leveraging contextual information from incoming requests.…

Finetuning large language models (LLMs) is essential for task adaptation, yet today's serving stacks isolate inference and finetuning on separate GPU clusters -- wasting resources and under-utilizing hardware. We introduce FlexLLM, the…

Ensembles of Deep Neural Networks (DNNs) have achieved qualitative predictions but they are computing and memory intensive. Therefore, the demand is growing to make them answer a heavy workload of requests with available computational…

Large language model (LLM) training today runs on clusters spanning thousands of GPUs. While this scale enables rapid model advances, developing, debugging, and performance-tuning the training framework inevitably becomes complex and…

End users face a choice between privacy and efficiency in current Large Language Model (LLM) service paradigms. In cloud-based paradigms, users are forced to compromise data locality for generation quality and processing speed. Conversely,…

Edge computing processes data where it is generated, enabling faster decisions, lower bandwidth usage, and improved privacy. However, edge devices typically operate under strict constraints on processing power, memory, and energy…

Deep learning (DL) shows its prosperity in a wide variety of fields. The development of a DL model is a time-consuming and resource-intensive procedure. Hence, dedicated GPU accelerators have been collectively constructed into a GPU…

With the growing complexity of modern integrated circuits, hardware engineers are required to devote more effort to the full design-to-manufacturing workflow. This workflow involves numerous iterations, making it both labor-intensive and…

Both the Mobile edge computing (MEC)-based and fog computing (FC)-aided Internet of Vehicles (IoV) constitute promising paradigms of meeting the demands of low-latency pervasive computing. To this end, we construct a dynamic NOMA-based…

Existing LLM serving strategies can be categorized based on whether prefill and decode phases are disaggregated: non-disaggregated (NoDG) or fully disaggregated (FuDG). However, the NoDG strategy leads to strong prefill-decode interference…

Serverless computing has emerged as a new execution model which gained a lot of attention in cloud computing thanks to the latest advances in containerization technologies. Recently, serverless has been adopted at the edge, where it can…

We present a framework for performance optimization in serverless edge-cloud platforms using dynamic task placement. We focus on applications for smart edge devices, for example, smart cameras or speakers, that need to perform processing…

The usage of large language models (LLMs) has grown increasingly fragmented, with no single model dominating. Meanwhile, cloud providers offer a wide range of mid-tier and older-generation GPUs that enjoy better availability and deliver…

With a recent trend of using Large Language Models (LLMs) for different applications within smart cities, there is a need for pushing these models toward the edge of network while still preserving their performance. Edge Computing (EC) as a…

Fine-tuning a large language model (LLM) using the local data of edge users can enable personalized services and applications. For privacy protection, the prevalent solution adopts distributed learning for fine-tuning and integrates…

Serving large generative models such as LLMs and multi- modal transformers requires balancing user-facing SLOs (e.g., time-to-first-token, time-between-tokens) with provider goals of efficiency and cost reduction. Existing solutions rely on…